[PATCH 3/3] sched: limit cpu search and rotate search window for scalability

[subhra mazumdar <subhra.mazumdar@oracle.com>]

Lower the lower limit of idle cpu search in select_idle_cpu() and also put
an upper limit. This helps in scalability of the search by restricting the
search window. Also rotating the search window with help of next_cpu
ensures any idle cpu is eventually found in case of high load.

Signed-off-by: subhra mazumdar <subhra.mazumdar@oracle.com>
---
 kernel/sched/fair.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d1d4769..62d585b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6279,7 +6279,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 	u64 avg_cost, avg_idle;
 	u64 time, cost;
 	s64 delta;
-	int cpu, nr = INT_MAX;
+	int cpu, target_tmp, nr = INT_MAX;
 
 	this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
 	if (!this_sd)
@@ -6297,15 +6297,24 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 
 	if (sched_feat(SIS_PROP)) {
 		u64 span_avg = sd->span_weight * avg_idle;
-		if (span_avg > 4*avg_cost)
+		if (span_avg > 2*avg_cost) {
 			nr = div_u64(span_avg, avg_cost);
-		else
-			nr = 4;
+			if (nr > 4)
+				nr = 4;
+		} else {
+			nr = 2;
+		}
 	}
 
+	if (per_cpu(next_cpu, target) != -1)
+		target_tmp = per_cpu(next_cpu, target);
+	else
+		target_tmp = target;
+
 	time = local_clock();
 
-	for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
+	for_each_cpu_wrap(cpu, sched_domain_span(sd), target_tmp) {
+		per_cpu(next_cpu, target) = cpu;
 		if (!--nr)
 			return -1;
 		if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
-- 
2.9.3